def prepare4saying(self, phrase, condition_matching_results, text_utils):
utterance = phrase.raw_text
# Если нужно сделать подстановку сматченных при проверке условия чанков.
if condition_matching_results and condition_matching_results.has_groups(
) and phrase.has_entries():
for name, group in condition_matching_results.groups.items():
group_ancor = name.upper()
if group_ancor in phrase.name2entry:
entry = phrase.name2entry[group_ancor]
words = group.words
# Нужно просклонять чанк?
if entry.tags:
tokens = group.phrase_tokens
target_tags = dict()
for tag in entry.tags:
if tag in ('ИМ', 'ВИН', 'РОД', 'ТВОР', 'ДАТ',
'ПРЕДЛ'):
target_tags['ПАДЕЖ'] = tag
else:
raise NotImplementedError()
words = normalize_chunk(tokens,
edges=None,
flexer=text_utils.flexer,
word2tags=text_utils.word2tags,
target_tags=target_tags)
# Подставляем слова чанка вместо подстроки $NP1(...)
entry_value = ' '.join(words)
utterance = utterance.replace(entry.raw_text, entry_value)
return utterance
def check_condition(self, bot, session, interlocutor, interpreted_phrase, answering_engine):
input_phrase = interpreted_phrase.interpretation
text_utils = answering_engine.text_utils
tokens = text_utils.tokenizer.tokenize(input_phrase)
tagsets = list(text_utils.postagger.tag(tokens))
lemmas = text_utils.lemmatizer.lemmatize(tagsets)
#edges = syntan.parse(tokens, tagsets)
# заглушка вместо парсинга:
edges = [(word, iword, None, None, None) for (iword, word) in enumerate(tokens)]
phrase_tokens = []
for word_index, (token, tagset, lemma) in enumerate(zip(tokens, tagsets, lemmas)):
t = PhraseToken()
t.word = token
t.norm_word = token.lower()
t.lemma = lemma[2]
t.tagset = tagset[1]
t.word_index = word_index
phrase_tokens.append(t)
chunks = text_utils.chunker.parse(tokens)
for chunk_index, chunk in enumerate(chunks):
phrase_tokens[chunk.tokens[0].index].is_chunk_starter = True
for token in chunk.tokens:
phrase_tokens[token.index].chunk_index = chunk_index
for mask in self.masks:
mx = match(phrase_tokens, mask.mask_terms)
if mx:
#print('{} groups in matching:'.format(mx.groups_count()))
res = RuleConditionMatching.create(True)
for group_name, tokens in mx.index2group.items():
normal_words = normalize_chunk(tokens, edges, text_utils.flexer, text_utils.word2tags)
#print('{}={} normal={}'.format(group_name, ' '.join(t.word for t in tokens), ' '.join(normal_words)))
res.add_group(group_name.upper(), normal_words, tokens)
return res
return RuleConditionMatching.create(False)
def check_condition(self, bot, session, interlocutor, interpreted_phrase,
answering_engine):
if self.is_raw:
input_phrase = interpreted_phrase.raw_phrase
else:
input_phrase = interpreted_phrase.interpretation
text_utils = answering_engine.text_utils
tokens = text_utils.tokenizer.tokenize(input_phrase)
tagsets = list(text_utils.postagger.tag(tokens))
lemmas = text_utils.lemmatizer.lemmatize(tagsets)
#edges = syntan.parse(tokens, tagsets)
# заглушка вместо парсинга:
edges = [(word, iword, None, None, None)
for (iword, word) in enumerate(tokens)]
phrase_tokens = []
for word_index, (token, tagset,
lemma) in enumerate(zip(tokens, tagsets, lemmas)):
t = PhraseToken()
t.word = token
t.norm_word = token.lower()
t.lemma = lemma[2]
t.tagset = tagset[1]
t.word_index = word_index
phrase_tokens.append(t)
chunks = text_utils.chunker.parse(tokens)
for chunk_index, chunk in enumerate(chunks):
phrase_tokens[chunk.tokens[0].index].is_chunk_starter = True
for token in chunk.tokens:
phrase_tokens[token.index].chunk_index = chunk_index
for mask in self.masks:
mx = match(phrase_tokens, mask.mask_terms)
if mx:
#print('{} groups in matching:'.format(mx.groups_count()))
res = RuleConditionMatching.create(True)
for group_name, tokens in mx.index2group.items():
normal_words1 = normalize_chunk(tokens, edges,
text_utils.flexer,
text_utils.word2tags)
normal_words2 = normalize_chunk(
tokens,
edges,
text_utils.flexer,
text_utils.word2tags,
target_tags={'ЧИСЛО': 'ЕД'})
normal_words = list(
set(normal_words1) | set(normal_words2))
if group_name in self.constraints_w2v:
constraints_satisfied = True
for c in self.constraints_w2v[group_name]:
hit = False
for chunk_word in normal_words:
sim = text_utils.word_similarity(
c.anchor, chunk_word)
if sim >= c.sim:
hit = True
break
if not hit:
constraints_satisfied = False
break
if not constraints_satisfied:
return RuleConditionMatching.create(False)
#print('{}={} normal={}'.format(group_name, ' '.join(t.word for t in tokens), ' '.join(normal_words)))
res.add_group(group_name.upper(), normal_words, tokens)
return res
return RuleConditionMatching.create(False)